Topic
Bounding overwatch
About: Bounding overwatch is a research topic. Over the lifetime, 966 publications have been published within this topic receiving 15156 citations.
Papers published on a yearly basis
Papers
More filters
Patent•
01 Jan 2019
TL;DR: In this paper, a bounding box is eliminated based on a comparison of its density and an average density across all bounding boxes, if its density is greater than a certain threshold, text elements are evaluated to determine whether the text element is bold.
Abstract: To identify emphasized text, bounding boxes are based on clusters resulting from horizontal compression and horizontal morphological dilation. The bounding boxes are processed to determine if any contain words or characters in bold. A bounding box is eliminated based on a comparison of its density and an average density across all bounding boxes. If its density is greater, text elements within the bounding box are evaluated to determine whether the text element is bold.
3 citations
TL;DR: This paper defines a new distance formulation between two convex polygons describing the overlapping degree and non-overlapping degree and proposes a loss called Polygon-to-Polygon distance loss (P2P Loss), which is continuous, differentiable, and inherently free from any RBBox definition.
Abstract: There are two key issues that limit further improvements in the performance of existing rotational detectors: 1) Periodic sudden change of the parameters in the rotating bounding box (RBBox) definition causes a numerical discontinuity in the loss (such as smoothL1 loss). 2) There is a gap of optimization asynchrony between the loss in the RBBox regression and evaluation metrics. In this paper, we define a new distance formulation between two convex polygons describing the overlapping degree and non-overlapping degree. Based on this smooth distance, we propose a loss called Polygon-to-Polygon distance loss (P2P Loss). The distance is derived from the area sum of triangles specified by the vertexes of one polygon and the edges of the other. Therefore, the P2P Loss is continuous, differentiable, and inherently free from any RBBox definition. Our P2P Loss is not only consistent with the detection metrics but also able to measure how far, as well as how similar, a RBBox is from another one even when they are completely non-overlapping. These features allow the RetinaNet using the P2P Loss to achieve 79.15% mAP on the DOTA dataset, which is quite competitive compared with many state-of-the-art rotated object detectors.
3 citations
05 Jul 2021
TL;DR: The method not only outperforms previous state-of-the-art methods in CUB-200-2011 and ILSVRC datasets but also gives more precise bounding box prediction when the IoU threshold is higher.
Abstract: Pseudo bounding box supervision is a promising approach for weakly supervised object localization (WSOL) with only image-level labels. However, the generated pseudo bounding boxes may be inaccurate or even completely non-overlapped with the objects of interest. In this paper, we propose to estimate the uncertainty of pseudo bounding boxes such that the negative impact caused by inaccurate estimation of pseudo supervision could be alleviated for better WSOL. The refined bounding boxes and corresponding variance uncertainties are learned by training a neural network regressor to penalize the erroneous estimations. To the best of our knowledge, this is the first work to incorporate uncertainty information of pseudo bounding boxes for WSOL. Experimental results show that our method not only outperforms previous state-of-the-art methods in CUB-200-2011 and ILSVRC datasets but also gives more precise bounding box prediction when the IoU threshold is higher.
3 citations
TL;DR: Zhang et al. as discussed by the authors proposed a method based on RetinaNet to detect lesion areas in colposcopic images, where the depth features of the entire image are extracted by a fusion of ResNet50 and a feature pyramid network (FPN).
3 citations
TL;DR: In this article , some improvements are proposed on the basis of the GIoU Loss function, taking into account the overlap rate of complete overlap of bounding boxes. But the results show that the AP of NGIoU loss function in the YOLOv4 model is 47.68%, 1.15% higher than that of the IoU loss, and the highest map value is 86.79%.
Abstract: Loss functions, such as the IoU Loss function and the GIoU (Generalized Intersection over Union) Loss function have been put forward to replace regression loss functions commonly used in regression loss calculation. GIoU Loss alleviates the vanishing gradient in the case of the non-overlapping, but it will completely degenerate into the IoU Loss function when bounding boxes overlap totally, which fails to achieve the optimization effect. To solve this problem, some improvements are proposed in this paper on the basis of the GIoU Loss function, taking into account the overlap rate of complete overlap of bounding boxes. In PASCAL VOC data, the experimental results demonstrate that the AP of NGIoU Loss function in the YOLOv4 model is 47.68%, 1.15% higher than that of the GIoU Loss function, and the highest map value is 86.79% in the YOLOv5 model.
3 citations